Context & Resources

update_context

Update an existing context item: change its name, body, collection, or project, or re-pull a tracked web page's content. Collection and project use full-replace semantics, so always pass both.

Parameters

Name	Type	Required	Default	Description
`context_item_id`	`string (uuid)`	Yes	—	The context item to update
`refresh_webpage`	`boolean`	No	—	Set `true` to re-pull a `webpage` item's content from its stored URL. Ignores `name` / `content` / `import_url`. Errors on non-webpage items. Admin/editor only
`name`	`string`	No	—	If provided, updates the name. Omit to leave unchanged. Ignored when `refresh_webpage` is true
`content`	`string`	No	—	New markdown body. Omit to leave unchanged. Triggers RAG re-embedding. Mutually exclusive with `import_url`. Ignored when `refresh_webpage` is true
`import_url`	`string`	No	—	Public URL — backend fetches and converts to clean markdown server-side, then stores it as a fresh one-off snapshot body. Mutually exclusive with `content`. Ignored when `refresh_webpage` is true
`collection_id`	`integer \| null`	Yes	—	Full replace. Pass the current ID to keep the item in its collection, pass a different ID to move it, or pass `null` (`0` works too) to move it back to the top level of the Reference Library
`project_id`	`string (uuid) \| null`	Yes	—	Full replace. Pass the current ID to keep the project association, pass a different ID to move it, or pass `null` to disassociate it

Input Schema

{
  "type": "object",
  "required": [
    "context_item_id",
    "collection_id",
    "project_id"
  ],
  "properties": {
    "name": {
      "type": "string",
      "description": "If provided, updates the name. Omit to leave unchanged. Ignored when refresh_webpage is true."
    },
    "content": {
      "type": "string",
      "description": "New markdown body. Omit to leave unchanged. Triggers RAG re-embedding. Mutually exclusive with import_url. Ignored when refresh_webpage is true."
    },
    "import_url": {
      "type": "string",
      "description": "Public URL — backend fetches and converts to clean markdown server-side, then stores it as a fresh one-off snapshot body. Mutually exclusive with content. Ignored when refresh_webpage is true."
    },
    "project_id": {
      "type": [
        "string",
        "null"
      ],
      "format": "uuid",
      "description": "Full replace. Pass the current ID to keep the project association, pass a different ID to move it, or pass null to disassociate it."
    },
    "collection_id": {
      "type": [
        "integer",
        "null"
      ],
      "description": "Full replace. Pass the current ID to keep the item in its collection, pass a different ID to move it, or pass null (0 works too) to move it back to the top level of the Reference Library."
    },
    "context_item_id": {
      "type": "string",
      "format": "uuid",
      "description": "The context item to update."
    },
    "refresh_webpage": {
      "type": "boolean",
      "description": "Set true to re-pull a webpage item's content from its stored URL. Ignores name / content / import_url. Errors on non-webpage items. Admin/editor only."
    }
  }
}

Output Schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Context item ID."
    },
    "name": {
      "type": "string",
      "description": "Updated context item name."
    },
    "content": {
      "type": "string",
      "description": "Updated reference content."
    },
    "link_url": {
      "type": "string",
      "description": "Direct URL to view this context item in the Marcora app."
    },
    "project_id": {
      "type": [
        "string",
        "null"
      ],
      "description": "Project this item is associated with (null if none)."
    },
    "updated_at": {
      "type": "integer",
      "description": "Unix timestamp of last update."
    },
    "word_count": {
      "type": "integer",
      "description": "Word count of updated content."
    },
    "collection_id": {
      "type": [
        "integer",
        "null"
      ],
      "description": "Collection this item belongs to (null if none)."
    },
    "content_intro": {
      "type": "string",
      "description": "Truncated content intro used in listings."
    },
    "relevancy_processed_status": {
      "type": "string",
      "description": "RAG re-processing status (unprocessed, provisional, complete). Flips to unprocessed whenever name or content changes."
    }
  }
}

Instructions

Use this tool to update an existing context item in your reference library.

What you can update:

name: rename the context item (omit to leave unchanged)
content: replace the stored reference content (omit to leave unchanged; triggers RAG re-embedding)
import_url: replace the body with a fresh one-off snapshot fetched from a public URL (omit to leave unchanged; mutually exclusive with content)
collection_id: move to a different collection, or pass null to move it back to the top level of the Reference Library
project_id: change the project association, or pass null to disassociate
refresh_webpage: set true to re-pull a tracked webpage item from its stored URL (admin/editor only; ignores name / content / import_url)

Important — full-replace semantics for collection_id and project_id:
Unlike name and content, you MUST pass collection_id and project_id on every call. Omitting them is NOT the same as keeping them unchanged — include the current values to preserve them. If you do not know the current values, call get_context_item first or use the web app to check before updating. (Even with refresh_webpage, pass the item's current values; the refresh does not change them.)

The two behave differently when omitted, so pass both explicitly: omitting collection_id returns a Missing param error, while omitting project_id silently detaches the item from its project.

Passing null:
Both fields accept a JSON null — the tool's input schema types them as ["integer","null"] / ["string","null"], so strict MCP clients can send null directly. Use it to move an item out of a collection and back to the top level of the Reference Library, or to detach it from a project. For collection_id, 0 is accepted as an alias for null.

Workflow:

Get the context_item_id (UUID) — use list_context_items, list_context_collections, get_project, or get_relevant_context to find IDs.
Pass collection_id and project_id (required, nullable) — include current values to preserve, or null to clear.
Optionally pass name and/or a new body (content or import_url) to update those fields, or refresh_webpage: true to re-pull a tracked web page.

Errors

400 — Provide either content or import_url, not both. (both were supplied)
400 — Failed to extract markdown from import_url (the URL could not be fetched or parsed)
400 — refresh_webpage used on a non-webpage item
403 — refresh_webpage requires admin or editor role

Example prompts

"Rename that brand voice context item to 'Brand Voice v2'"
"Move the competitive analysis out of the 'Archive' collection"
"Update our pricing context with the new Enterprise tier info"
"I updated our pricing page — refresh that web-page context item"
"Re-import the Acme snapshot from https://example.com/competitor-pricing"